Supervised Video Summarization On Summe
Metriken
F1-score (Canonical)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | F1-score (Canonical) |
|---|---|
| supervised-video-summarization-via-multiple | 51.6 |
| joint-video-summarization-and-moment | 54.5 |
| relational-reasoning-over-spatial-temporal | 53.4 |
| supervised-video-summarization-via-multiple | 48 |
| clip-it-language-guided-video-summarization | 54.2 |
| combining-global-and-local-attention-with | 55.6 |
| supervised-video-summarization-via-multiple | 44.9 |
| hierarchical-multimodal-transformer-to | 44.1 |
| video-joint-modelling-based-on-hierarchical | 50.6 |
| supervised-video-summarization-via-multiple | 43.1 |
| deep-reinforcement-learning-for-unsupervised | 42.1 |
| query-twice-dual-mixture-attention-meta | 54.3 |
| csta-cnn-based-spatiotemporal-attention-for | - |
| combining-global-and-local-attention-with | 57.1 |
| video-summarization-based-on-video-text | 48.7 |
| supervised-video-summarization-via-multiple | 53.4 |
| dsnet-a-flexible-detect-to-summarize-network | 50.2 |
| align-and-attend-multimodal-summarization | 55.0 |
| supervised-video-summarization-via-multiple | 44.4 |
| discriminative-feature-learning-for | 48.6 |
| video-summarization-based-on-video-text | 50.7 |